Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nclamvn/openclawvn --skill eldercare-sosgit clone --depth 1 https://github.com/nclamvn/openclawvnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nclamvn/openclawvn/eldercare-sos)<a href="https://agentmods.dev/skills/nclamvn/openclawvn/eldercare-sos"><img src="https://agentmods.dev/badge/skills/nclamvn/openclawvn/eldercare-sos/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nclamvn/openclawvn/eldercare-sos"><img src="https://agentmods.dev/badge/skills/nclamvn/openclawvn/eldercare-sos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.02651 |
| Opus 5 | $0.00049 | $0.01326 |
| Sonnet 5 | $0.00020 | $0.00530 |
| Haiku 4.5 | $0.00010 | $0.00265 |
Grade A, and why
eldercare-sos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eldercare SOS — Hệ thống khẩn cấp
Skill này xử lý tình huống khẩn cấp cho bà nội. Khi được trigger, nó thực hiện escalation chain tự động: Zalo → Phone → gọi tất cả gia đình.
Khi nào skill này được trigger
1. Nút SOS vật lý (qua Home Assistant)
Bà hoặc ông bấm nút Zigbee. Kiểm tra entity sensor.sos_button_action:
| Hành động | Giá trị sensor | Xử lý |
|---|---|---|
| Bấm 1 lần | single |
Bắt đầu từ Level 1 (Zalo trước) |
| Bấm 2 lần | double |
Skip Level 1, vào thẳng Level 2 (gọi điện) |
| Giữ 3 giây | long |
Skip Level 1+2, vào thẳng Level 3 (gọi TẤT CẢ) |
2. AI auto-detect (từ eldercare-monitor)
Khi skill eldercare-monitor phân loại mức KHẨN CẤP → trigger SOS bắt đầu từ Level 2 (vì AI đã xác nhận nghiêm trọng).
2b. Fall Detection (từ eldercare-fall-detect)
Khi skill eldercare-fall-detect phát hiện ngã VÀ bà không phản hồi TTS xác nhận (2 lần, tổng 45 giây) → trigger SOS bắt đầu từ Level 2. Source = "fall_detect". Kèm theo 2 ảnh camera snapshot (trước và sau TTS).
3. Manual (gia đình gõ chat)
Khi ai đó gõ "SOS", "cứu", "khẩn cấp" trong Zalo hoặc Telegram → trigger từ Level 1.
QUAN TRỌNG: Kiểm tra duplicate
Trước khi bắt đầu SOS mới, kiểm tra memory eldercare_sos_active:
- Nếu đã có SOS active (
resolved= false) → KHÔNG tạo SOS mới - Log: "SOS đã active từ {triggered_at}. Không tạo duplicate."
- Nếu SOS cũ đã resolve → tiếp tục tạo mới
Hành động tức thì (T+0, MỌI level)
Ngay khi SOS trigger, thực hiện ĐỒNG THỜI:
1. Bật đèn phòng bà sáng tối đa
Dùng tool home_assistant:
action: call_service
domain: light
service: turn_on
target_entity_id: light.grandma_room
service_data: { "brightness": 255 }
2. TTS thông báo cho bà qua loa (VOLUME CAO)
Dùng tool home_assistant:
action: call_service
domain: tts
service: speak
target_entity_id: media_player.grandma_room
service_data: {
"message": "Bà ơi, đã gửi tín hiệu cho người nhà rồi ạ. Người nhà sẽ liên lạc ngay!",
"language": "vi"
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 278 lines · 99 tokens per session scan A 174b6f72684f
eldercare-sos is a skill published in the GitHub repository nclamvn/openclawvn (56 stars, last pushed 6mo ago), licensed MIT. It adds 99 tokens to every session and 2,651 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.